StudentSim: Training LLM-based Student Simulators

• URL: http://arxiv.org/abs/2609.01591v1
• Date: Tue, 01 Sep 2026 17:55:10 GMT
• Title: StudentSim: Training LLM-based Student Simulators
• Abstract summary: StudentSim is a training framework that turns sparse per-student data into individualized simulators.<n>The resulting simulators both mirror a student's own responses and update them under tutor guidance.<n>Across all three domains, StudentSim outperforms GPT-5.4 on both metrics.
• Score: 67.06331010637008
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approaches are limited: state-tracking models fit student behavior but struggle to process explanations or corrections, while LLM role-play follows guidance fluently but does not reliably match the competence of the student being imitated. We present StudentSim, a training framework that turns sparse per-student data into individualized simulators through pooled training followed by per-student specialization. The resulting simulators both mirror a student's own responses and update them under tutor guidance. We also introduce StudentSimEval, a standardized protocol covering 60 students across chess, second-language English writing, and mathematics, using public learner datasets with de-identified records shared for research. StudentSimEval measures behavioral fidelity (F), or how well a simulator matches a student's responses, and guidance responsiveness (R), or how readily it updates under tutor guidance, with all methods fit and evaluated on the same records. Across all three domains, StudentSim outperforms GPT-5.4 on both metrics. In chess, StudentSim reaches F=0.51 and R=0.91, compared with 0.23 and 0.72 for GPT-5.4 and 0.45 and 0.27 for Maia2. As a proof of concept, using StudentSim as a reward model for tutor reinforcement learning produces a chess tutor that expert humans rate as more accurate, better-guided, and more personalized than a no-RL baseline and a tutor trained against a GPT-5.4 simulator reward. Code is available at https://github.com/microsoft/StudentSim.

Related papers

• Simulating Disengaged Students to Evaluate LLM-based Tutors [0.40105987447353786]
  Disengagement-Aware Student Simulators (DAS2) models five learner-engagement states: engaged, gaming, wheel-spinning, off-task, and mixed.<n>DAS2 provides a pre-deployment framework for evaluating how AI tutors respond to diverse learner-engagement states before deployment.
  arXiv  Detail & Related papers  (2026-09-11T01:28:48Z)
• IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking [59.6657632820611]
  IR-SIM is a skill-native navigation simulator designed for rapid scenario construction, benchmarking, and robot learning.<n> scenarios are entirely defined by YAML configuration files that specify mobile robot kinematics, geometric collision checking, LiDAR sensing, visualization, and behavior modules.<n>The experiments showcase the convenience and versatility of IR-SIM in multiple tasks.
  arXiv  Detail & Related papers  (2026-06-07T16:55:37Z)
• Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues [42.74448763964845]
  We introduce the task of history-conditioned student simulation.<n>The goal is to accurately predict student dialogue turns by leveraging information in the student's learning history.<n>We train both components with reinforcement learning (RL), yielding profiles optimized for faithful student simulation.
  arXiv  Detail & Related papers  (2026-05-28T15:02:51Z)
• Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators [55.617099475539305]
  Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI tutors and human educators.<n>Yet such simulators are typically evaluated by output similarity to real students, not by whether they behave like students with coherent misconceptions during interaction.<n>We introduce a controlled framework for evaluating misconception faithfulness, whether a simulator maintains a misconception-driven belief state and updates selectively when feedback addresses the underlying misconception.
  arXiv  Detail & Related papers  (2026-05-12T20:55:23Z)
• Mind the Sim2Real Gap in User Simulation for Agentic Tasks [101.69142591891234]
  We formalize the Sim2Real gap in user simulation and present the first study running the full $$-bench protocol with real humans.<n> Behaviorally, LLM simulators are excessively cooperative, stylistically uniform, and lack realistic frustration or ambiguity.<n>These findings highlight the importance of human validation when using LLM-based user simulators in the agent development cycle.
  arXiv  Detail & Related papers  (2026-03-11T19:12:31Z)
• SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants? [61.07963107032645]
  Large language models (LLMs) are increasingly used in interactive applications.<n>Human evaluation remains the gold standard for assessing their performance in multi-turn conversations.<n>We introduce SimulatorArena, a benchmark of 909 annotated human-LLM conversations on two interactive tasks.
  arXiv  Detail & Related papers  (2025-10-06T23:17:44Z)
• Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents [36.704574105201864]
  Large language models (LLMs) are revolutionizing education, with LLM-based agents playing a key role in simulating student behavior.<n>A major challenge in student simulation is modeling the diverse learning patterns of students at various cognitive levels.
  arXiv  Detail & Related papers  (2025-05-26T13:48:49Z)
• Promptable Closed-loop Traffic Simulation [57.36568236100507]
  ProSim is a multimodal promptable closed-loop traffic simulation framework. ProSim rolls out a traffic scenario in a closed-loop manner, modeling each agent's interaction with other traffic participants. To support research on promptable traffic simulation, we create ProSim-Instruct-520k, a multimodal prompt-scenario paired driving dataset.
  arXiv  Detail & Related papers  (2024-09-09T17:59:15Z)
• Generalisable Methods for Early Prediction in Interactive Simulations for Education [5.725477071353353]
  Classifying students' interaction data in the simulations based on their expected performance has the potential to enable adaptive guidance. We first measure the students' conceptual understanding through their in-task performance. Then, we suggest a novel type of features that, starting from clickstream data, encodes both the state of the simulation and the action performed by the student.
  arXiv  Detail & Related papers  (2022-07-04T14:46:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.